Keming Wu

wukeming11's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a Space 5 days ago

Running on Zero

Agents

4

Aero Realtime 4B

📺

4

Proactive real-time commentary on audio-video streams

authored a paper 12 days ago

VGI-Bench: Probing Visual Intelligence in Video Generation Models

Paper • 2608.19583 • Published 14 days ago • 179

upvoted a paper 12 days ago

VGI-Bench: Probing Visual Intelligence in Video Generation Models

Paper • 2608.19583 • Published 14 days ago • 179

updated a collection 18 days ago

StreamOPD

Collection

StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding • 2 items • Updated 18 days ago

authored a paper 19 days ago

StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding

Paper • 2608.16320 • Published 23 days ago • 10

updated 2 collections 19 days ago

StreamOPD

Collection

StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding • 2 items • Updated 18 days ago

WorldReasonBench

Collection

WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors • 3 items • Updated 19 days ago

upvoted a paper 20 days ago

StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding

Paper • 2608.16320 • Published 23 days ago • 10

updated a model 22 days ago

UniX-Lab/StreamOPD-4B-ST-CueGate

Video-Text-to-Text • 5B • Updated 22 days ago • 64

published a model 22 days ago

UniX-Lab/StreamOPD-4B-ST-CueGate

Video-Text-to-Text • 5B • Updated 22 days ago • 64

liked a model 27 days ago

Qwen/Qwen3.8-2.4T-A95B

Text Generation • 2.4T • Updated 27 days ago • 52.7k • • 1.21k

liked a model 28 days ago

kcz358/aero-realtime-4B

Video-Text-to-Text • 5B • Updated 26 days ago • 332 • 9

upvoted a paper about 2 months ago

Evidence-Grounded AI for Musculoskeletal Care

Paper • 2607.12527 • Published Jul 14 • 17

liked a dataset 3 months ago

longvideotool/LongVT-Source

Viewer • Updated Dec 10, 2025 • 100 • 2k • 5

upvoted a paper 3 months ago

MMAE: A Massive Multitask Audio Editing Benchmark

Paper • 2606.07229 • Published Jun 5 • 46

authored 2 papers 3 months ago

WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors

Paper • 2605.10434 • Published May 11 • 30

ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning

Paper • 2605.20342 • Published May 19 • 34

upvoted a paper 4 months ago

ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning

Paper • 2605.20342 • Published May 19 • 34